Charging regulation model for electric vehicles on the road

Patent metadata

Field	Value
Publication number	US-11719547-B2
Application number	US-202016830560-A
Country	US
Kind code	B2
Filing date	Mar 26, 2020
Priority date	Mar 26, 2020
Publication date	Aug 8, 2023
Grant date	Aug 8, 2023

Abstract

A computer-implemented method for determining whether an electric vehicle (EV) requires a current charge. The method analyzes a set of EV data, wherein the set of EV data comprises a battery level, a destination, a current position, and a predicted arrival time to the destination. The method further constructs a charging regulation model for the EV, based on the analyzed set of EV data. The method further computes a risk score pertaining to charging the EV, based on the constructed charging regulation model for the EV, and determines whether the EV requires a current charge based on the computed risk score. The method further engages one or more wireless charging points on a roadway, if the computed risk score is below a threshold value.

First claim

The invention claimed is:

1. A computer-implemented method for determining whether an electric vehicle (EV) is to be provided a charge, the method comprising:
analyzing a set of EV data, wherein the set of EV data comprises a battery level, a destination, a current position, and a predicted arrival time to the destination;
constructing a charging regulation model for the EV, based on the analyzed set of EV data;
computing a risk score pertaining to charging the EV as the EV travels along a roadway, based on the constructed charging regulation model for the EV;
based on the computed risk score being above a threshold value, determining that the EV is to be provided a charge as the EV travels on the roadway; and
based on determining that the EV is to be provided a charge as the EV travels on the roadway, selectively engaging, according to a minimum additional battery charge, one or more wireless charging points on the roadway to provide the charge to the EV as the EV travels on the roadway, wherein the selectively engaging comprise engaging the one or more wireless charging points to provide the minimum additional battery charge and disengaging at least one wireless charging point based on detecting that the minimum additional battery charge has been provided to the EV.

2. The computer-implemented method of claim 1 , wherein the charging regulation model is a logic regression model.

3. The computer-implemented method of claim 1 , wherein constructing the charging regulation model further comprises:
predicting traffic congestion for the EV to reach the destination; and
calculating a minimum amount of battery charge for the EV to reach the destination, based on the predicted traffic congestion.

4. The computer-implemented method of claim 1 , wherein computing a risk score pertaining to charging the EV further comprises:
receiving a rate of battery charge usage per mile for the EV, a mileage amount to reach the destination, predicted traffic congestion along a route to reach the destination, and a rate of battery charge usage per hour for the EV;
if an amount of time to reach the destination is equal to, or exceeds, a current battery charge level, then the computed risk score is above the threshold value; and
if an amount of time to reach the destination is not equal to, or does not exceed, a current battery charge level, then the computed risk score is below the threshold value.

5. The computer-implemented method of claim 4 , further comprising:
determining how much additional battery charge is to be provided to the EV to reach the destination, based on the computed risk score.

6. The computer-implemented method of claim 1 , further comprising:
determining one or more loss metrics over time based on training and feedback from a user of the EV.

7. The computer-implemented method of claim 1 , further comprising:
notifying the EV, prior to entering the roadway, that the EV will not be charged due to traffic congestion.

8. A computer program product, comprising a non-transitory tangible storage device having program code embodied therewith, the program code executable by a processor of a computer to perform a method, the method comprising:
analyzing a set of electric vehicle (EV) data, wherein the set of EV data comprises a battery level, a destination, a current position, and a predicted arrival time to the destination;
constructing a charging regulation model for the EV, based on the analyzed set of EV data;
computing a risk score pertaining to charging the EV as the EV travels along a roadway, based on the constructed charging regulation model for the EV;
based on the computed risk score being above a threshold value, determining that the EV is to be provided a charge as the EV travels on the roadway; and
based on determining that the EV is to be provided a charge as the EV travels on the roadway, selectively engaging, according to a minimum additional battery charge, one or more wireless charging points on the roadway to provide the charge to the EV as the EV travels on the roadway, wherein the selectively engaging comprise engaging the one or more wireless charging points to provide the minimum additional battery charge and disengaging at least one wireless charging point based on detecting that the minimum additional battery charge has been provided to the EV.

9. The computer program product of claim 8 , wherein the charging regulation model is a logic regression model.

10. The computer program product of claim 8 , wherein constructing the charging regulation model further comprises:
predicting traffic congestion for the EV to reach the destination; and
calculating a minimum amount of battery charge for the EV to reach the destination, based on the predicted traffic congestion.

11. The computer program product of claim 8 , wherein computing a risk score pertaining to charging the EV further comprises:
receiving a rate of battery charge usage per mile for the EV, a mileage amount to reach the destination, predicted traffic congestion along a route to reach the destination, and a rate of battery charge usage per hour for the EV;
if an amount of time to reach the destination is equal to, or exceeds, a current battery charge level, then the computed risk score is above the threshold value; and
if an amount of time to reach the destination is not equal to, or does not exceed, a current battery charge level, then the computed risk score is below the threshold value.

12. The computer program product of claim 11 , further comprising:
determining how much additional battery charge is to be provided to the EV to reach the destination, based on the computed risk score.

13. The computer program product of claim 8 , further comprising:
determining one or more loss metrics over time based on training and feedback from a user of the EV.

14. The computer program product of claim 8 , further comprising:
notifying the EV, prior to entering the roadway, that the EV will not be charged due to traffic congestion.

15. A computer system, comprising:
one or more computer devices each having one or more processors and one or more tangible storage devices; and
a program embodied on at least one of the one or more storage devices, the program having a plurality of program instructions for execution by the one or more processors, the program instructions comprising instructions for:
analyzing a set of electric vehicle (EV) data, wherein the set of EV data comprises a battery level, a destination, a current position, and a predicted arrival time to the destination;
constructing a charging regulation model for the EV, based on the analyzed set of EV data;
computing a risk score pertaining to charging the EV as the EV travels along a roadway, based on the constructed charging regulation model for the EV;
based on the computed risk score being above a threshold value, determining that the EV is to be provided a charge as the EV travels on the roadway; and
based on determining that the EV is to be provided a charge as the EV travels on the roadway, selectively engaging, according to a minimum additional battery charge, one or more wireless charging points on the roadway to provide the charge to the EV as the EV travels on the roadway, wherein the selectively engaging comprise engaging the one or more wireless charging points to provide the minimum additional battery charge and disengaging at least one wireless charging point based on detecting that the minimum additional battery charge has been provided to the EV.

16. The computer system of claim 15 , wherein the charging regulation

Assignees

• Kyndryl Inc

Inventors

• Treadway Michael
• Trim Craig M
• Liang Chen
• Kwatra Shikhar
• Fox Jeremy R
• Blee Joseph

Classifications

• G01C21/3469 Primary

  Fuel consumption; Energy use; Emission aspects · CPC title

• B60L53/12 Primary

  Inductive energy transfer · CPC title

• B60L58/10

  for monitoring or controlling batteries · CPC title

• G06N20/00

  Machine learning · CPC title

• G01S19/42

  Determining position · CPC title